Merge branch 'net-vhost-improve-performance-when-enable-busyloop'

Tonghao Zhang says:

====================
net: vhost: improve performance when enable busyloop

This patches improve the guest receive performance.
On the handle_tx side, we poll the sock receive queue
at the same time. handle_rx do that in the same way.

For more performance report, see patch 4
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 92 insertions, 79 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 1bff6bc8161a..015abf333c62 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -480,33 +480,94 @@ signal_used:
 	nvq->batched_xdp = 0;
 }
 
+static int sock_has_rx_data(struct socket *sock)
+{
+	if (unlikely(!sock))
+		return 0;
+
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
+	return skb_queue_empty(&sock->sk->sk_receive_queue);
+}
+
+static void vhost_net_busy_poll_try_queue(struct vhost_net *net,
+					  struct vhost_virtqueue *vq)
+{
+	if (!vhost_vq_avail_empty(&net->dev, vq)) {
+		vhost_poll_queue(&vq->poll);
+	} else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+		vhost_disable_notify(&net->dev, vq);
+		vhost_poll_queue(&vq->poll);
+	}
+}
+
+static void vhost_net_busy_poll(struct vhost_net *net,
+				struct vhost_virtqueue *rvq,
+				struct vhost_virtqueue *tvq,
+				bool *busyloop_intr,
+				bool poll_rx)
+{
+	unsigned long busyloop_timeout;
+	unsigned long endtime;
+	struct socket *sock;
+	struct vhost_virtqueue *vq = poll_rx ? tvq : rvq;
+
+	mutex_lock_nested(&vq->mutex, poll_rx ? VHOST_NET_VQ_TX: VHOST_NET_VQ_RX);
+	vhost_disable_notify(&net->dev, vq);
+	sock = rvq->private_data;
+
+	busyloop_timeout = poll_rx ? rvq->busyloop_timeout:
+				     tvq->busyloop_timeout;
+
+	preempt_disable();
+	endtime = busy_clock() + busyloop_timeout;
+
+	while (vhost_can_busy_poll(endtime)) {
+		if (vhost_has_work(&net->dev)) {
+			*busyloop_intr = true;
+			break;
+		}
+
+		if ((sock_has_rx_data(sock) &&
+		     !vhost_vq_avail_empty(&net->dev, rvq)) ||
+		    !vhost_vq_avail_empty(&net->dev, tvq))
+			break;
+
+		cpu_relax();
+	}
+
+	preempt_enable();
+
+	if (poll_rx || sock_has_rx_data(sock))
+		vhost_net_busy_poll_try_queue(net, vq);
+	else if (!poll_rx) /* On tx here, sock has no rx data. */
+		vhost_enable_notify(&net->dev, rvq);
+
+	mutex_unlock(&vq->mutex);
+}
+
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
-				    struct vhost_net_virtqueue *nvq,
+				    struct vhost_net_virtqueue *tnvq,
 				    unsigned int *out_num, unsigned int *in_num,
 				    struct msghdr *msghdr, bool *busyloop_intr)
 {
-	struct vhost_virtqueue *vq = &nvq->vq;
-	unsigned long uninitialized_var(endtime);
-	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
+	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
+	struct vhost_virtqueue *rvq = &rnvq->vq;
+	struct vhost_virtqueue *tvq = &tnvq->vq;
+
+	int r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov),
 				  out_num, in_num, NULL, NULL);
 
-	if (r == vq->num && vq->busyloop_timeout) {
+	if (r == tvq->num && tvq->busyloop_timeout) {
 		/* Flush batched packets first */
-		if (!vhost_sock_zcopy(vq->private_data))
-			vhost_tx_batch(net, nvq, vq->private_data, msghdr);
-		preempt_disable();
-		endtime = busy_clock() + vq->busyloop_timeout;
-		while (vhost_can_busy_poll(endtime)) {
-			if (vhost_has_work(vq->dev)) {
-				*busyloop_intr = true;
-				break;
-			}
-			if (!vhost_vq_avail_empty(vq->dev, vq))
-				break;
-			cpu_relax();
-		}
-		preempt_enable();
-		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
+		if (!vhost_sock_zcopy(tvq->private_data))
+			// vhost_net_signal_used(tnvq);
+			vhost_tx_batch(net, tnvq, tvq->private_data, msghdr);
+
+		vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false);
+
+		r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov),
 				      out_num, in_num, NULL, NULL);
 	}
 
@@ -856,7 +917,7 @@ static void handle_tx(struct vhost_net *net)
 	struct vhost_virtqueue *vq = &nvq->vq;
 	struct socket *sock;
 
-	mutex_lock(&vq->mutex);
+	mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX);
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
@@ -897,16 +958,6 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
 	return len;
 }
 
-static int sk_has_rx_data(struct sock *sk)
-{
-	struct socket *sock = sk->sk_socket;
-
-	if (sock->ops->peek_len)
-		return sock->ops->peek_len(sock);
-
-	return skb_queue_empty(&sk->sk_receive_queue);
-}
-
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 				      bool *busyloop_intr)
 {
@@ -914,41 +965,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
 	struct vhost_virtqueue *rvq = &rnvq->vq;
 	struct vhost_virtqueue *tvq = &tnvq->vq;
-	unsigned long uninitialized_var(endtime);
 	int len = peek_head_len(rnvq, sk);
 
-	if (!len && tvq->busyloop_timeout) {
+	if (!len && rvq->busyloop_timeout) {
 		/* Flush batched heads first */
 		vhost_net_signal_used(rnvq);
 		/* Both tx vq and rx socket were polled here */
-		mutex_lock_nested(&tvq->mutex, 1);
-		vhost_disable_notify(&net->dev, tvq);
-
-		preempt_disable();
-		endtime = busy_clock() + tvq->busyloop_timeout;
-
-		while (vhost_can_busy_poll(endtime)) {
-			if (vhost_has_work(&net->dev)) {
-				*busyloop_intr = true;
-				break;
-			}
-			if ((sk_has_rx_data(sk) &&
-			     !vhost_vq_avail_empty(&net->dev, rvq)) ||
-			    !vhost_vq_avail_empty(&net->dev, tvq))
-				break;
-			cpu_relax();
-		}
-
-		preempt_enable();
-
-		if (!vhost_vq_avail_empty(&net->dev, tvq)) {
-			vhost_poll_queue(&tvq->poll);
-		} else if (unlikely(vhost_enable_notify(&net->dev, tvq))) {
-			vhost_disable_notify(&net->dev, tvq);
-			vhost_poll_queue(&tvq->poll);
-		}
-
-		mutex_unlock(&tvq->mutex);
+		vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true);
 
 		len = peek_head_len(rnvq, sk);
 	}
@@ -1063,7 +1086,7 @@ static void handle_rx(struct vhost_net *net)
 	__virtio16 num_buffers;
 	int recv_pkts = 0;
 
-	mutex_lock_nested(&vq->mutex, 0);
+	mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX);
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index b13c6b4b2c66..f52008bb8df7 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -294,8 +294,11 @@ static void vhost_vq_meta_reset(struct vhost_dev *d)
 {
 	int i;
 
-	for (i = 0; i < d->nvqs; ++i)
+	for (i = 0; i < d->nvqs; ++i) {
+		mutex_lock(&d->vqs[i]->mutex);
 		__vhost_vq_meta_reset(d->vqs[i]);
+		mutex_unlock(&d->vqs[i]->mutex);
+	}
 }
 
 static void vhost_vq_reset(struct vhost_dev *dev,
@@ -891,20 +894,6 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 #define vhost_get_used(vq, x, ptr) \
 	vhost_get_user(vq, x, ptr, VHOST_ADDR_USED)
 
-static void vhost_dev_lock_vqs(struct vhost_dev *d)
-{
-	int i = 0;
-	for (i = 0; i < d->nvqs; ++i)
-		mutex_lock_nested(&d->vqs[i]->mutex, i);
-}
-
-static void vhost_dev_unlock_vqs(struct vhost_dev *d)
-{
-	int i = 0;
-	for (i = 0; i < d->nvqs; ++i)
-		mutex_unlock(&d->vqs[i]->mutex);
-}
-
 static int vhost_new_umem_range(struct vhost_umem *umem,
 				u64 start, u64 size, u64 end,
 				u64 userspace_addr, int perm)
@@ -954,7 +943,10 @@ static void vhost_iotlb_notify_vq(struct vhost_dev *d,
 		if (msg->iova <= vq_msg->iova &&
 		    msg->iova + msg->size - 1 >= vq_msg->iova &&
 		    vq_msg->type == VHOST_IOTLB_MISS) {
+			mutex_lock(&node->vq->mutex);
 			vhost_poll_queue(&node->vq->poll);
+			mutex_unlock(&node->vq->mutex);
+
 			list_del(&node->node);
 			kfree(node);
 		}
@@ -986,7 +978,6 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 	int ret = 0;
 
 	mutex_lock(&dev->mutex);
-	vhost_dev_lock_vqs(dev);
 	switch (msg->type) {
 	case VHOST_IOTLB_UPDATE:
 		if (!dev->iotlb) {
@@ -1020,7 +1011,6 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 		break;
 	}
 
-	vhost_dev_unlock_vqs(dev);
 	mutex_unlock(&dev->mutex);
 
 	return ret;